Connect Clinicaltrials and your agent gets 50 tools, among them ai_visibility_check, ask_pipeworx, ask_pipeworx_beta. It answers at https://gateway.pipeworx.io/clinicaltrials/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 23 October 2026, succeeded.
Search and analyze ClinicalTrials.gov: trials by keyword/condition/drug/status/phase, one study's…
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ai_visibility_check | Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model. Default model is Workers AI Llama-3.3-70b (free); pass `_apiKey` to also probe Anthropic (BYO key — you pay Anthrop Inputs: entity, context, models, _apiKey |
ask_pipeworx | PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS economic statistics, government records, USPTO patents, ATTOM real estate, weather, clinical trials, news, stocks, crypto, sports, a Inputs: question, query, q, prompt, text, input |
ask_pipeworx_beta | Beta version of ask_pipeworx: identical universal router (same 6,061 tools, same arguments, same response shape) with candidate routing improvements enabled live whenever one is under test. No candidate is active right now (the last was ret Inputs: question, query, q, prompt, text, input |
ask_pipeworx_grounded | Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 6,061 across 1572 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result cont Inputs: question, query, q, prompt, text, input |
bet_research | Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-kristi-noem-win-the-2028-republican-presidential-nomination"), a polymarket.com URL, or a question text. Prefer an UNDATED slug: a Inputs: market, depth, include_raw |
company_facts | TYPED, DETERMINISTIC financial facts for a US public company for an EXPLICITLY NAMED reporting period — "Apple revenue for fiscal 2023", "Walmart net income FY2026 Q3", "Microsoft cash at the end of fiscal 2024". PREFER OVER entity_profile Inputs: company, attribute, period, freshness, max_age, as_of |
compare_entities | "Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over seque Inputs: type, values |
ct_catalyst_calendar | Find trials with sponsor-entered primary-completion or study-completion dates in a specified window. These registry dates may be estimated or revised and are planning signals—not guaranteed data readouts, conference presentations, or regula Inputs: query, sponsor, sponsor_match, event_type, from_date, to_date |
ct_compare_sponsors | Compare 2–5 NAMED lead sponsors on ClinicalTrials.gov under identical condition, recruitment-status, and phase filters. Returns full matching counts, a ranked comparison, and a small study sample for each sponsor. Use for questions like "wh Inputs: sponsors, condition, status, phase, sample_limit |
ct_competitive_landscape | Map registered interventional trials for a condition and optional intervention across sponsors, phases, statuses, and interventions. The output reflects a bounded registry sample, not market share, scientific differentiation, or an exhausti Inputs: condition, intervention, status, phase, sample_size |
ct_count_by_condition | Count clinical trials for a condition or disease, broken down by recruitment status and by trial phase — how many are recruiting, completed, terminated, and how many are Phase 1, 2, 3 or 4. Use for landscape questions about how much trial a Inputs: condition, status, phase |
ct_enrollment_watch | Route active trials for enrollment follow-up using registry status, enrollment type, dates, last update, and site counts. Flags are mechanical review hints—not predictions of recruitment success, trial failure, or data timing. Inputs: query, sponsor, sponsor_match, phase, limit |
ct_get_study | Get full trial details by NCT ID (e.g., 'NCT04567890'). Returns protocol, eligibility criteria, primary outcomes, sponsor, locations, and results. Inputs: nct_id |
ct_phase_transition_rates | Measure how often drugs for a disease actually advance from one clinical phase to the next — the registry-derived analog of a probability-of-technical-success (PTRS) benchmark. Groups industry-sponsored interventional trials for the conditi Inputs: condition, sponsor_class, from_year, to_year, censor_years, max_pages |
ct_recent_updates | Track recent ClinicalTrials.gov activity by a specific event class within a verifiable date window. Three DISTINCT recency events, chosen via date_type: "last_update" (any edit to a study, ~5k/week — the default), "first_posted" (a study ne Inputs: date_type, since, until, status, query, limit |
ct_results_summary | Project posted ClinicalTrials.gov results for one NCT ID, including registered endpoints, reported outcome measures, statistical analyses, and adverse-event group counts. Registry results are not an FDA conclusion, peer review, or investmen Inputs: nct_id, max_outcomes |
ct_search | Search ClinicalTrials.gov for clinical trials — find trials and look up a NAMED trial by keyword, condition, drug/therapy, status (e.g. 'Recruiting'), or phase (e.g. 'Phase 2'). Use for "clinical trials for <disease/drug>", or to locate a s Inputs: query, status, phase, sponsor_match, sponsor, limit |
ct_sponsor_activity | Track a sponsor’s newly registered studies, first-posted results, or study updates within a verifiable date window. Registry activity is not necessarily a corporate disclosure or material event. Inputs: sponsor, sponsor_match, date_type, since, until, limit |
ct_sponsor_pipeline | Summarize a sponsor’s ClinicalTrials.gov portfolio by phase, status, condition, and intervention from a bounded relevance-ranked sample, while reporting the full matching count. Registration does not establish asset ownership, probability o Inputs: sponsor, sponsor_match, status, phase, sample_size |
ct_sponsor_trials | List the trials a company LEADS on ClinicalTrials.gov, by sponsor or organization name. Returns status, phase, and conditions to map a research pipeline. Matches the registered lead-sponsor field, so trials another organisation runs using t Inputs: sponsor_match, sponsor, status, phase, limit |
ct_trials_by_location | Find clinical trials near a LOCATION. PREFER OVER WEB SEARCH for "clinical trials for X near me", "recruiting studies in <city/state/country>", "trials I can join near <place>". Filter by condition + a place name (city/state/country) OR lat Inputs: condition, location, lat, lon, radius_mi, status |
deep_research | ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 15 Inputs: question, depth |
discover_tools | Find tools by describing the data or task. Use when you need to browse, search, look up, or discover what tools exist for: SEC filings, financials, revenue, profit, FDA drugs, adverse events, FRED economic data, Census demographics, BLS job Inputs: query, task, q, description, search, limit |
entity_profile | "Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in O Inputs: type, value |
forget | Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall. Inputs: key |
generate_llms_txt | Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output i Inputs: url, max_links |
kalshi_weather_edge | Prices Kalshi daily high-temperature markets against the NWS forecast for the market's OWN settlement station, and measures whether that forecast actually beats the market. Two modes. LIVE (default): returns the full strike ladder for one c Inputs: city, series_ticker, date, market_type, backtest_days |
list_subscriptions | List the caller's active subscriptions. Returns id, type, params, created_at, last_fired_at, fire_count for each. Use this to review what you're monitoring before adding more or to find an id to cancel. Inputs: include_inactive |
pipeworx_feedback | Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise Inputs: type, message, context, claim_token |
pipeworx_trending | What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming Inputs: window |
polymarket_arbitrage | Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a `trending_scan` of the top ~200 markets by weekly volume; pass `event` for the strongest per-event partition_check, or `t Inputs: event, topic |
polymarket_edge_tracker | Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinking?" — a fresh wide edge and a 3-week-old wide edge are different trades (the latter is wide for a re Inputs: days, window |
polymarket_edges | Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped int Inputs: window, limit, min_edge_pp, slippage_pp, category_filter, min_kelly |
polymarket_fill_risk | Realizable-vs-theoretical edge check against live CLOB order-book depth. REQUIRES one of `market` (single-market mode) or `event` (basket/partition mode). SINGLE-MARKET: pass a market slug/URL + side (buy_yes|sell_yes|buy_no|sell_no, defaul Inputs: market, event, side, size_usd |
polymarket_kalshi_spread | Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real Inputs: topic, kalshi_event_ticker, polymarket_event_slug |
recall | Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scrat Inputs: key |
recent_alerts | Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. Inputs: type, since, limit, unread_only, mark_read |
recent_changes | "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE paralle Inputs: type, value, since |
release_calendar_markets | JOIN of the official release calendar (econ data, the FOMC, FDA decisions, SEC rules) against LIVE Polymarket/Kalshi markets — which scheduled releases land in the next N hours, and which live markets resolve on them. This is a POSITIONING Inputs: hours, categories |
remember | Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't hav Inputs: key, value |
resolution_audit, resolution_diff, resolve_entity, scan_competitor_ai_presence, scan_dependency, search_within, subscribe, suggest_questions, unsubscribe, validate_claim
Every block below points at https://gateway.pipeworx.io/clinicaltrials/mcp. Pick your client and copy.
claude mcp add --transport http clinicaltrials https://gateway.pipeworx.io/clinicaltrials/mcp
{
"mcpServers": {
"clinicaltrials": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://gateway.pipeworx.io/clinicaltrials/mcp"]
}
}
}{
"mcpServers": {
"clinicaltrials": {
"url": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}{
"servers": {
"clinicaltrials": {
"type": "http",
"url": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}{
"context_servers": {
"clinicaltrials": {
"url": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}{
"mcpServers": {
"clinicaltrials": {
"serverUrl": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}{
"mcpServers": {
"clinicaltrials": {
"url": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}name: Clinicaltrials
version: 0.0.1
schema: v1
mcpServers:
- name: Clinicaltrials
type: streamable-http
url: https://gateway.pipeworx.io/clinicaltrials/mcp{
"mcpServers": {
"clinicaltrials": {
"httpUrl": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}{
"mcpServers": {
"clinicaltrials": {
"type": "http",
"url": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}{
"mcpServers": {
"clinicaltrials": {
"url": "https://gateway.pipeworx.io/clinicaltrials/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fgateway.pipeworx.io%2Fclinicaltrials%2Fmcp&type=streamable_http&id=clinicaltrials&name=Clinicaltrials
It answered our last check on 23 October 2026 in 81 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
50, as returned by the server's own tools/list on 17 September 2026: ai_visibility_check, ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, bet_research, company_facts, compare_entities, ct_catalyst_calendar, and 42 more.
It answered our last check on 23 October 2026 in 81 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://gateway.pipeworx.io/clinicaltrials/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.pipeworx-io. Endpoint host: gateway.pipeworx.io. ARD identifier: urn:air:io.github.pipeworx-io:mcp:clinicaltrials.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.